Skip to content

Commit eb1424d

Browse files
Merge pull request #2301 from yangnicole-ml/patch-3
Update nvv4-retirement.md
2 parents d5d9b4d + 0581620 commit eb1424d

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

articles/virtual-machines/sizes/gpu-accelerated/nvv4-retirement.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -23,7 +23,7 @@ On September 30, 2026, Microsoft Azure will retire the Standard_NV4as_v4, Standa
2323

2424
Microsoft is recommending the Azure [NVads_V710_v5-series](/azure/virtual-machines/sizes/gpu-accelerated/nvadsv710-v5-series?tabs=sizebasic) VMs, which offer greater GPU memory bandwidth per GPU. The NVads_V710_v5-series VMs take advantage of the AMD Simultaneous Multithreading technology to assign dedicated vCPU threads to each VM and support NVMe for ephemeral local storage capability.
2525

26-
The NVads_V710_v5-series enables right-sizing for demanding GPU-accelerated graphics applications and cloud-based virtual desktops to provide a seamless end user experience while providing a cost-effective choice for a full range of graphics-enabled virtual desktop experiences. The VMs are also sized to deliver high-quality, interactive gaming experiences in the cloud, optimized for rendering and streaming complex graphics. In addition, the NVads_V710_v5-series supports small to medium AI/ML inference workloads such as Small Language Model (SLMs), recommendation systems, and semantic indexing, by taking advantage of the computational IP blocks in the Radeon Pro V710 GPUs.
26+
The NVads_V710_v5-series enables right-sizing for demanding GPU-accelerated graphics applications and cloud-based virtual desktops to provide a seamless end user experience while providing a cost-effective choice for a full range of graphics-enabled virtual desktop experiences. The VMs are also sized to deliver high-quality, interactive gaming experiences in the cloud, optimized for rendering and streaming complex graphics. In addition, the NVads_V710_v5-series supports small AI inference workloads such as Small Language Model (SLMs), recommendation systems, and semantic indexing, by taking advantage of the computational IP blocks in the Radeon Pro V710 GPUs.
2727

2828
|Workload|Recommended SKU to Migrate to|
2929
| -------- | -------- |

0 commit comments

Comments
 (0)